self-healing-claudex
OfficialAutonomous dual-review loop for trusted builds.
Authorm2ai-portfolio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill automates end-to-end build-and-review loops that pair a Claude-driven Planner/Builder with Codex-driven adversarial review to converge on a safe, correct build.
Core Features & Use Cases
- Autonomous loop orchestration: coordinates planning, building, and adversarial review across rounds.
- Safety and coverage discipline: enforces spec-claims, PLAN.md tests, and coverage gaps checks; surfaces actionable findings.
- Lifecycle state management: atomic state, round transitions, and summarized outcomes for user review.
- Use Case: A team wants to continuously validate a codebase by cycling through planner, builder, and Codex review until no substantive findings remain or max rounds are reached.
Quick Start
Start a self-healing claudex loop with a concrete topic to orchestrate a build-and-review cycle.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: self-healing-claudex Download link: https://github.com/m2ai-portfolio/m2ai-skills-pack/archive/main.zip#self-healing-claudex Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.